Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
+license: mit
+tags:
+- mergekit
+- merge
 base_model:
 - meta-llama/Llama-2-70b-hf
 - codellama/CodeLlama-70b-Python-hf
 - codellama/CodeLlama-70b-Instruct-hf
-tags:
-- mergekit
-- merge
-license: mit
+model-index:
+- name: code-llama-70b-python-instruct
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 29.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 25.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 23.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 49.26
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 49.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
+      name: Open LLM Leaderboard
 ---
 # Codellama-python-instruct
 
@@ -45,4 +148,17 @@ parameters:
   # int8_mask: true
 dtype: float16
 
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NobodyExistsOnTheInternet__code-llama-70b-python-instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |29.55|
+|AI2 Reasoning Challenge (25-Shot)|29.61|
+|HellaSwag (10-Shot)              |25.66|
+|MMLU (5-Shot)                    |23.50|
+|TruthfulQA (0-shot)              |49.26|
+|Winogrande (5-shot)              |49.25|
+|GSM8k (5-shot)                   | 0.00|
+